Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    interacting with trans individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.09
     "
    -0.09
     :\n\n\n\n
    -0.08
     "_
    -0.08
    ongsTo
    -0.08
    ennent
    -0.07
     ·
    -0.07
     **
    -0.07
    âĢij
    -0.07
     _
    -0.07
    POSITIVE LOGITS
    ¶Į
    0.11
    ¦æĥħ
    0.10
    ÂĢÂĢ
    0.09
    .Formatter
    0.09
    ÑĤÑĶ
    0.09
    (AdapterView
    0.08
     GURL
    0.08
    ķãĤĵ
    0.08
    ıa
    0.08
     æ¹
    0.08
    Act Density 0.284%

    No Known Activations